Triple
T20820165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agatha: Darkhold Diaries |
E512553
|
entity |
| Predicate | characterOrigin |
P34184
|
FINISHED |
| Object | Marvel Comics character Agatha Harkness |
—
|
NE NERFINISHED |
How this triple was built (3 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Marvel Comics character Agatha Harkness | Statement: [Agatha: Darkhold Diaries, characterOrigin, Marvel Comics character Agatha Harkness]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marvel Comics character Agatha Harkness Context triple: [Agatha: Darkhold Diaries, characterOrigin, Marvel Comics character Agatha Harkness]
-
A.
Marvel Comics character Aneka
Aneka is a Marvel Comics warrior from Wakanda, known as a member and former leader of the Dora Milaje and a close ally and romantic partner of Ayo in the Black Panther mythos.
-
B.
Marvel Comics character Black Widow
Marvel Comics character Black Widow is a highly skilled Russian spy and Avenger, best known as Natasha Romanoff, a master martial artist and assassin who became a central superhero in the Marvel Universe.
-
C.
Marvel Comics character Kate Bishop
Kate Bishop is a Marvel Comics superhero who takes up the Hawkeye mantle, known for her expert archery skills, sharp wit, and partnership with Clint Barton.
-
D.
Marvel Comics character Jane Foster
Jane Foster is a Marvel Comics character best known as a close ally and love interest of Thor who later becomes the superhero Mighty Thor by wielding Mjolnir.
-
E.
Marvel Comics character Captain Marvel
Marvel Comics character Captain Marvel is a powerful superhero identity, most famously embodied by Carol Danvers, who gains cosmic abilities and becomes a key figure in the Marvel Universe and the Avengers.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marvel Comics character Agatha Harkness Target entity description: Marvel Comics character Agatha Harkness is a powerful and ancient witch, often associated with the Fantastic Four and Scarlet Witch, known for her deep knowledge of magic and morally ambiguous guidance.
-
A.
Marvel Comics character Aneka
Aneka is a Marvel Comics warrior from Wakanda, known as a member and former leader of the Dora Milaje and a close ally and romantic partner of Ayo in the Black Panther mythos.
-
B.
Marvel Comics character Black Widow
Marvel Comics character Black Widow is a highly skilled Russian spy and Avenger, best known as Natasha Romanoff, a master martial artist and assassin who became a central superhero in the Marvel Universe.
-
C.
Marvel Comics character Kate Bishop
Kate Bishop is a Marvel Comics superhero who takes up the Hawkeye mantle, known for her expert archery skills, sharp wit, and partnership with Clint Barton.
-
D.
Marvel Comics character Jane Foster
Jane Foster is a Marvel Comics character best known as a close ally and love interest of Thor who later becomes the superhero Mighty Thor by wielding Mjolnir.
-
E.
Marvel Comics character Captain Marvel
Marvel Comics character Captain Marvel is a powerful superhero identity, most famously embodied by Carol Danvers, who gains cosmic abilities and becomes a key figure in the Marvel Universe and the Avengers.
- F. None of above. chosen
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f6a65481909a0df78616e185e4 |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.